Mohammad Faisal
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Mohammad Faisal has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Halima Sadia
Integral University
4 shared publications - Shweta Dwivedi
Integral University
4 shared publications - Mohammed Siddique
Faculty of Information Technology, Majan University College
2 shared publications - Nashra Javed
Advanced Computing & Research Lab., Department of Computer Application, Integral University, Lucknow, India
2 shared publications - Sonali Yadav
Integral University, Lucknow, India
2 shared publications - Subrata Jana
Department of Mathematics, Jadavpur University, Kolkata, India
2 shared publications
Latest Publications
- 30 January 2026
- Published by Springer Nature
- p. 389-433
Fuzzy Logic in Smart Traffic Management System for Cities: An Overview
- 30 January 2026
- Published by Springer Nature
- p. 389-433
Fuzzy Logic in Smart Traffic Management System for Cities: An Overview
- Open Access
- 1 January 2026
- Published by GN1 Sistemas e Publicacoes Ltd. in ITEGAM-Journal of Engineering and Technology for Industrial Applications (ITEGAM-JETIA)
- Vol. 12 (61) , 895-904
AN ENSEMBLE-ORIENTED HYBRID XNS APPROACH FOR DETECTING ABNORMAL BEHAVIOR IN SOCIAL NETWORKS
The rapid rise of online social networks (OSNs) has significantly reshaped how people communicate and share information, but it has also brought growing concerns around user security, privacy, and overall well-being. Identifying abnormal behavior—such as the spread of fake news, sharing malicious links, or engaging in harmful online activities—has become increasingly important for ensuring safer digital environments. To address these challenges, this study introduces an ensemble-oriented hybrid XNS framework that combines XGBoost, Support Vector Machine (SVM), and Naïve Bayesian Classifier (NBC) in a cascaded architecture, designed to improve detection accuracy and robustness. The proposed framework draws on a rich set of features extracted from both user profiles and user-generated content, allowing for a more comprehensive understanding of user behavior patterns. It is trained and tested using a combination of synthetic and real-world datasets, ensuring that the model remains adaptable and reliable across diverse scenarios. In addition to conventional anomaly detection, the framework also places special emphasis on identifying users who may show signs of depression or suicidality, thereby supporting early intervention and promoting mental health awareness. Experimental results demonstrate that the model achieves an accuracy of approximately 97%, outperforming traditional methods and highlighting its potential as a scalable and efficient solution for enhancing both cybersecurity and user well-being in modern social networks.
- 1 January 2026
- Published by GN1 Sistemas e Publicacoes Ltd. in ITEGAM-Journal of Engineering and Technology for Industrial Applications (ITEGAM-JETIA)
- Vol. 12 (61) , 895-904
Open AccessAN ENSEMBLE-ORIENTED HYBRID XNS APPROACH FOR DETECTING ABNORMAL BEHAVIOR IN SOCIAL NETWORKS
The rapid rise of online social networks (OSNs) has significantly reshaped how people communicate and share information, but it has also brought growing concerns around user security, privacy, and overall well-being. Identifying abnormal behavior—such as the spread of fake news, sharing malicious links, or engaging in harmful online activities—has become increasingly important for ensuring safer digital environments. To address these challenges, this study introduces an ensemble-oriented hybrid XNS framework that combines XGBoost, Support Vector Machine (SVM), and Naïve Bayesian Classifier (NBC) in a cascaded architecture, designed to improve detection accuracy and robustness. The proposed framework draws on a rich set of features extracted from both user profiles and user-generated content, allowing for a more comprehensive understanding of user behavior patterns. It is trained and tested using a combination of synthetic and real-world datasets, ensuring that the model remains adaptable and reliable across diverse scenarios. In addition to conventional anomaly detection, the framework also places special emphasis on identifying users who may show signs of depression or suicidality, thereby supporting early intervention and promoting mental health awareness. Experimental results demonstrate that the model achieves an accuracy of approximately 97%, outperforming traditional methods and highlighting its potential as a scalable and efficient solution for enhancing both cybersecurity and user well-being in modern social networks.
- 20 May 2025
- Published by Springer Nature
- p. 431-452
Enhancing Fuzzy Multi Criteria Decision Making Technique in Engineering Design Problem
- 20 May 2025
- Published by Springer Nature
- p. 431-452
Enhancing Fuzzy Multi Criteria Decision Making Technique in Engineering Design Problem
- 20 May 2025
- Published by Springer Nature
- p. 307-324
Improving Diabetic Patient Care Through Fuzzy Logic: A Comprehensive Approach
- 20 May 2025
- Published by Springer Nature
- p. 307-324
Improving Diabetic Patient Care Through Fuzzy Logic: A Comprehensive Approach
- 11 April 2025
- Published by IGI Global Scientific Publishing
- p. 561-602
Transforming Healthcare
IoT technologies, combined with machine learning (ML), are revolutionizing healthcare through remote patient monitoring, personalized treatment, and operational optimization. This section defines healthcare IoT, highlighting its attributes and evolution. It examines the impact of wearable sensors, IoT devices, and smart equipment on patient outcomes and clinical processes. The chapter also discusses ML applications in healthcare, focusing on clinical decision support, data processing, and outcome modeling. It explores how ML enhances diagnostics and treatment, integrating IoT for proactive disease management and early intervention. Challenges such as regulatory compliance, data privacy, and system interoperability are addressed, along with future research directions.
- 11 April 2025
- Published by IGI Global Scientific Publishing
- p. 561-602
Transforming Healthcare
IoT technologies, combined with machine learning (ML), are revolutionizing healthcare through remote patient monitoring, personalized treatment, and operational optimization. This section defines healthcare IoT, highlighting its attributes and evolution. It examines the impact of wearable sensors, IoT devices, and smart equipment on patient outcomes and clinical processes. The chapter also discusses ML applications in healthcare, focusing on clinical decision support, data processing, and outcome modeling. It explores how ML enhances diagnostics and treatment, integrating IoT for proactive disease management and early intervention. Challenges such as regulatory compliance, data privacy, and system interoperability are addressed, along with future research directions.
- Open Access
- 15 March 2025
- Published by Science Research Society in Journal of Information Systems Engineering and Management
- Vol. 10 (21s) , 890-898
Implementation and Validation of a Digital Privacy Framework for Crowdsourced IoT Data Processing
The proposed privacy-preserving crowdsourcing framework integrates IoT-based anomaly detection with differential privacy, homomorphic encryption, and federated learning. The framework protects data gathering, anonymization, and processing while ensuring accurate outcomes. The framework is built using Flask and Isolation Forest, which ensures the balance between utility and privacy while providing security for crowdsourced IoT applications for real-world deployment.
- 15 March 2025
- Published by Science Research Society in Journal of Information Systems Engineering and Management
- Vol. 10 (21s) , 890-898
Open AccessImplementation and Validation of a Digital Privacy Framework for Crowdsourced IoT Data Processing
The proposed privacy-preserving crowdsourcing framework integrates IoT-based anomaly detection with differential privacy, homomorphic encryption, and federated learning. The framework protects data gathering, anonymization, and processing while ensuring accurate outcomes. The framework is built using Flask and Isolation Forest, which ensures the balance between utility and privacy while providing security for crowdsourced IoT applications for real-world deployment.
- 27 December 2024
- Published by Springer Nature in International Journal of Bullying Prevention
- Vol. 8 (2) , 1-20
An Efficacy Comparison of Supervised Machine Learning Classifiers for Cyberbullying Detection and Prediction
- 27 December 2024
- Published by Springer Nature in International Journal of Bullying Prevention
- Vol. 8 (2) , 1-20
An Efficacy Comparison of Supervised Machine Learning Classifiers for Cyberbullying Detection and Prediction
- 9 October 2024
- Published by Springer Nature
- p. 531-544
Exploring the Issues and Challenges in Crowdsourcing: An Empirical Investigation
- 9 October 2024
- Published by Springer Nature
- p. 531-544
Exploring the Issues and Challenges in Crowdsourcing: An Empirical Investigation
- 1 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 12, 1224-1229
Framework for Optimizing Cloud Workflow Scheduling with the Krill Herd Algorithm
Cloud computing has revolutionized the way compu-tational resources are provisioned and managed, offering scalability, flexibility, and cost-efficiency. Effective workflow scheduling in dynamic cloud environments is paramount to harness these benefits. In this paper, we introduce a novel workflow scheduling framework centered on the Krill Herd Algorithm (KHA). Our approach aims to optimize task allocation and resource utilization while meeting service-level agreements (SLAs) in diverse cloud computing scenarios. The paper begins with a detailed system model, providing insights into the dynamic nature of cloud environments and the associated scheduling challenges. We present the methodology, highlighting the adaptability and efficiency of KHA in addressing real-time changes and resource allocation dynamics. To evaluate our framework, comprehensive experiments are conducted, leveraging key performance metrics, including Task Completion Time (TCT), Resource Utilization (RU), Makespan (MS), and SLA Compliance. Results reveal the superiority of our approach over existing methods, with consistent improvements in task completion efficiency, resource optimization, reduced turnaround times, and SLA adherence.
- 1 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 12, 1224-1229
Framework for Optimizing Cloud Workflow Scheduling with the Krill Herd Algorithm
Cloud computing has revolutionized the way compu-tational resources are provisioned and managed, offering scalability, flexibility, and cost-efficiency. Effective workflow scheduling in dynamic cloud environments is paramount to harness these benefits. In this paper, we introduce a novel workflow scheduling framework centered on the Krill Herd Algorithm (KHA). Our approach aims to optimize task allocation and resource utilization while meeting service-level agreements (SLAs) in diverse cloud computing scenarios. The paper begins with a detailed system model, providing insights into the dynamic nature of cloud environments and the associated scheduling challenges. We present the methodology, highlighting the adaptability and efficiency of KHA in addressing real-time changes and resource allocation dynamics. To evaluate our framework, comprehensive experiments are conducted, leveraging key performance metrics, including Task Completion Time (TCT), Resource Utilization (RU), Makespan (MS), and SLA Compliance. Results reveal the superiority of our approach over existing methods, with consistent improvements in task completion efficiency, resource optimization, reduced turnaround times, and SLA adherence.
- 15 April 2023
- Published by Springer Nature
- p. 345-361
A Framework for Smart Agriculture System to Monitor the Crop Stress and Drought Stress Using Sentinel-2 Satellite Image
- 15 April 2023
- Published by Springer Nature
- p. 345-361
A Framework for Smart Agriculture System to Monitor the Crop Stress and Drought Stress Using Sentinel-2 Satellite Image